---
license: cc-by-nc-4.0
base_model:
- naver/DUSt3R_ViTLarge_BaseDecoder_224_linear
pipeline_tag: image-to-3d
---

This repository contains the model for the paper [MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds](https://huggingface.co/papers/2412.06974).

Code: https://github.com/facebookresearch/mvdust3r